ISCA Archive Eurospeech 1999
ISCA Archive Eurospeech 1999

Time-frequency principal components of speech: application to speaker identification

Ivan Magrin-Chagnolleau, Geoffrey Durou

In this paper, we propose a formalism, called vector filtering of spectral trajectories, which allows to integrate under a common formalism a lot of speech parameterization approaches. We then propose a new filtering in this framework, called time-frequency principal components (TFPC) of speech. We apply this new filtering in the framework of speaker identification, using a subset of the POLYCOST database. The results show an improvement of roughly 20 % compared to the use of the classical cepstral coefficients augmented by their coefficients.


doi: 10.21437/Eurospeech.1999-184

Cite as: Magrin-Chagnolleau, I., Durou, G. (1999) Time-frequency principal components of speech: application to speaker identification. Proc. 6th European Conference on Speech Communication and Technology (Eurospeech 1999), 759-762, doi: 10.21437/Eurospeech.1999-184

@inproceedings{magrinchagnolleau99_eurospeech,
  author={Ivan Magrin-Chagnolleau and Geoffrey Durou},
  title={{Time-frequency principal components of speech: application to speaker identification}},
  year=1999,
  booktitle={Proc. 6th European Conference on Speech Communication and Technology (Eurospeech 1999)},
  pages={759--762},
  doi={10.21437/Eurospeech.1999-184}
}